In privacy-preserving machine learning, differentially private stochasti...
Image diffusion models such as DALL-E 2, Imagen, and Stable Diffusion ha...
In this paper, we ask whether Vision Transformers (ViTs) can serve as an...
Representation learning, i.e. the generation of representations useful f...
Our work focuses on addressing sample deficiency from low-density region...
We focus on the use of proxy distributions, i.e., approximations of the
...
Understanding the fundamental limits of robust supervised learning has
e...
We ask the following question: what training information is required to
...
Evaluation of adversarial robustness is often error-prone leading to
ove...
Federated learning has emerged recently as a promising solution for
dist...
Open-world machine learning (ML) combines closed-world models trained on...
With increasing expressive power, deep neural networks have significantl...
Localized adversarial patches aim to induce misclassification in machine...
In safety-critical but computationally resource-constrained applications...
Deep neural networks have achieved impressive performance in many
applic...
A large body of recent work has investigated the phenomenon of evasion
a...